Skill Claude CodeCodex
Force full re-index zero downtime. Builds new versioned collection in background while search continues on current. Alias switches atomically when done. Requires explicit user confirmation — NEVER invoke automatically.
Skill Claude CodeCodex
Index/reindex codebase. First time — register alias + index in one command (index-codebase --name). Already indexed — incremental reindex (only changed files).
Skill Claude CodeCodex
Signal-driven review of merge request or local branch — rank diff risks via tea-rags (blast radius, fragile zones, silo style, missing tests, doc invariants, cycles), emit plain-language comments each naming a concrete fix. Triggers on "review this MR ", "review MR/PR", "проведи ревью MR", "сделай ревью ветки"…
Skill Claude CodeCodex
Internal strategy for explore skill. Find all pattern implementations across codebase. SEED → EXPAND → DEDUPLICATE → GROUP.
Skill Claude CodeCodex
Multi-preset breadth-first scan for refactoring candidates. Explore invokes when antipattern/refactoring intent broad-scope (no specific entity).
Skill Claude CodeCodex
Help the user file a high-quality GitHub issue for a TeaRAGs bug — gather environment + diagnostic context, CHECK FOR EXISTING/KNOWN ISSUES FIRST, then produce a pre-filled issue URL (or gh issue create when available). Triggers on "report a bug", "file an issue", "open a GitHub issue about this error / the…
Skill Claude CodeCodex
Assess project/domain health — scan risk zones across dimensions (bugs, hotspots, tech debt). Use when asked evaluate risks, find problematic areas, assess code health, identify zones needing attention — NOT for specific bug symptoms (use bug-hunt instead).
Skill Claude CodeCodex
Five recipes turn DSL test chunks into review / verify / refactor / TDD enrichment. Owned by tea-rags, used by dinopowers wrappers and other tea-rags skills.
Skill Claude CodeCodex
Define new normalized 0-1 ranking signal computed from raw payload fields at rerank time, registered under trajectory provider (git or static). Triggers on "add freshness signal", "new churn metric", "score code by ownership", "новый сигнал для git churn". NOT for adding rerank preset combining existing signals — use…
Skill Claude CodeCodex
Request/response shape exposed via public API to MCP tools, lives in api/public/dto. Triggers on "add DTO", "new request type for X tool", "add response shape", "новый DTO для tool'а". NOT for internal types — those live in contracts/, not public API surface.
Skill Claude CodeCodex
Add chunker hook splitting a language's source files into searchable chunks (classes, functions, comments) in ingest pipeline. Triggers on "add Kotlin support", "improve TypeScript class chunking", "fix Ruby comment extraction", "add language X". NOT for tweaking generic chunker behavior — edit chunker base directly…
Skill Claude CodeCodex
Expose new tool to LLM clients via MCP protocol — schema, handler, App method, docs in one coordinated change. Triggers on "add MCP tool", "new endpoint that returns X", "expose Y as a tool", "новый MCP tool". NOT for modifying an existing tool's schema — just edit the tool file directly.
Skill Claude CodeCodex
Add migration to existing pipeline (schema, snapshot, sparse) to upgrade persisted on-disk state. Triggers on "new Qdrant index", "backfill payload field", "snapshot format change", "rebuild sparse vectors", "новая миграция". NOT for code-only changes that don't touch persisted state on disk.
Skill Claude CodeCodex
Named ranking strategy combining derived signals with weights + overlay mask, exposed as enum option to MCP tools. Triggers on "new tech-debt preset", "create hotspot detector", "security-audit ranking", "rank by ownership and churn". NOT for adding single signal — use add-derived-signal for that.
Skill Claude CodeCodex
Analyze latest pipeline debug log for perf bottlenecks, timing issues, anomalies. Use when indexing slow, git blame too long, or pipeline behavior unexpected.
Skill Claude CodeCodex
Raise coverage above threshold via high-level behavioral tests hitting the exact uncovered branches. Never chase lines. tea-rags finds WHAT is untested; you write scenarios.
Skill Claude CodeCodex
Eval-driven skill optimization. Use when skill needs improvement — wrong tool selection, missing use cases, verbose instructions, stale rules. Structured eval cycles with parallel subagents measure skill quality, iterate until 100% pass rate.
Skill Claude CodeCodex
Index current tea-rags worktree as separate tea-rags-worktree project alias, verify end-to-end reindexing on worktree's own source. Auto-invoke when user asks to "test reindexing", "проверить реиндексацию", "test tea-rags self-reindex", "регрессия реиндексации", "test self-reindex on worktree", "smoke test enrichment…